{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:28:48Z","timestamp":1763202528788,"version":"build-2065373602"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8]]},"abstract":"<jats:p>Learning from label proportions (LLP) aims at learning an instance-level classifier with label proportions in grouped training data. Existing deep learning based LLP methods utilize end-to-end pipelines to obtain the proportional loss with Kullback-Leibler divergence between the bag-level prior and posterior class distributions. However, the unconstrained optimization on this objective can hardly reach a solution in accordance with the given proportions. Besides, concerning the probabilistic classifier, this strategy unavoidably results in high-entropy conditional class distributions at the instance level. These issues further degrade the performance of the instance-level classification. In this paper, we regard these problems as noisy pseudo labeling, and instead impose the strict proportion consistency on the classifier with a constrained optimization as a continuous training stage for existing LLP classifiers. In addition, we introduce the mixup strategy and symmetric cross-entropy to further reduce the label noise. Our framework is model-agnostic, and demonstrates compelling performance improvement in extensive experiments, when incorporated into other deep LLP models as a post-hoc phase.<\/jats:p>","DOI":"10.24963\/ijcai.2021\/377","type":"proceedings-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:00:49Z","timestamp":1628679649000},"page":"2737-2743","source":"Crossref","is-referenced-by-count":10,"title":["Two-stage Training for Learning from Label Proportions"],"prefix":"10.24963","author":[{"given":"Jiabin","family":"Liu","sequence":"first","affiliation":[{"name":"AI Lab, Samsung Research China - Beijing, University of Chinese Academy of Sciences"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[{"name":"University of International Business and Economics"}]},{"given":"Xin","family":"Shen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Zhiquan","family":"Qi","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}]},{"given":"Yingjie","family":"Tian","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}]}],"member":"10584","event":{"number":"30","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2021","name":"Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}","start":{"date-parts":[[2021,8,19]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2021,8,27]]}},"container-title":["Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:02:55Z","timestamp":1628679775000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2021\/377"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2021\/377","relation":{},"subject":[],"published":{"date-parts":[[2021,8]]}}}